Computer vision has come a long way since Imagenet, a large, open-source data set of labeled images, was released in 2009 for researchers to use to train AI—but images with tricky or bad lighting can still confuse algorithms.
A new paper by researchers from MIT and DeepMind details a process that can identify images in different lighting without having to hand-code rules or train on a huge data set. The process, called a rendered intrinsics network (RIN), automatically separates an image into reflectance, shape, and lighting layers. It then recombines the layers into a reconstruction of the original images.
In a paper published on the ArXiv, researchers from the University of California and Adobe have outlined a way for AI to not only learn a person’s style but create computer-generated images of items that match that style. This kind of computer vision task is being called “predictive fashion” and could let retailers create personalized pieces of clothing.
Reference: Kang, Wang-Cheng, Chen Fang, Zhaowen Wang, and Julian McAuley. “Visually-Aware Fashion Recommendation and Design with Generative Image Models.” arXiv:1711.02231 [Cs], November 6, 2017. http://arxiv.org/abs/1711.02231.
I wonder if Peter Burke would rethink the documental and historical status of photography when we start to see AI and Deep Learning systems (like generative adversarial networks – GANs) being used to create fake and believable images at scale.